Generates a file tree and identifies key architectural files.
AI agents call code_map to retrieve information from Git Context without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and structures existing repository information for presentation purposes. It performs no modifications, deletions, or external operations. It is a read-only operation that queries the Git repository structure to provide architectural insights to the AI agent.
From the tool's definition Tool generates a file tree and identifies key architectural files. Description explicitly states the server provides context 'without modifying or uploading code.' The verb 'generates' here means synthesizes/presents existing information.
Attacks that exploit this kind of access
Generates a file tree and identifies key architectural files. It is categorised as a Read tool in the Git Context MCP Server, which means it retrieves data without modifying state.
Register the Git Context MCP server in PolicyLayer and add a rule for code_map: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Git Context. Nothing to install.
code_map is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the code_map rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for code_map. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
code_map is provided by the Git Context MCP server (tamishaks-2/git-context-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →